Method for predicting dessert of overpressure low-permeability gas reservoir based on granularity reconstruction seepage evaluation model

By reconstructing the seepage evaluation model with granularity and combining neural networks and three-dimensional seismic attributes, the natural sweet spots of offshore overpressure and low-permeability gas reservoirs can be accurately identified, solving the identification problem in existing technologies and improving drilling hit rate and development effect.

CN122287308APending Publication Date: 2026-06-26HAINAN BRANCH OF CHINA NATIONAL OFFSHORE OIL (CHINA) CO LTD
3 Cites 0 Cited by

Patent Information

Application Number
CN202610328927.0
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2026-03-18
Publication Date
2026-06-26

AI Technical Summary

Technical Problem

Existing technologies struggle to accurately identify naturally occurring "sweet spots" within offshore overpressured, low-permeability gas reservoirs that possess industrial flow capabilities, resulting in low drilling success rates and unsatisfactory development outcomes.

Method used

A seepage evaluation model based on particle size reconstruction is adopted. Multivariate nonlinear fitting is performed through neural network algorithm. Combined with core particle size and well logging curve data, a natural seepage capacity index and energy factor are defined to construct a comprehensive index of natural sweet spots. Combined with three-dimensional seismic attribute volume, the accurate identification of natural sweet spots is achieved.

Benefits of technology

It has enabled accurate prediction of natural sweet spots in overpressured and low-permeability gas reservoirs, improved drilling hit rate, and enhanced development results.

✦ Generated by Eureka AI based on patent content.
Patent Text Reader

Abstract

The invention provides an overpressure low permeability gas reservoir sweet spot prediction method based on a granularity reconstruction seepage evaluation model, and the method comprises the steps: obtaining a rock core granularity prediction model through the training of a neural network algorithm based on rock core granularity analysis data and a conventional logging curve, and obtaining the rock core granularity prediction model by means of a Kozeny-Carman equation and a rock core mercury injection data fitting coefficient. Obtaining a conversion model of the core granularity and the pore throat radius, and reconstructing the conversion model into a brand new evaluation model coupling the seepage capacity and the stratum energy attribute by defining a natural seepage capacity index, an energy factor and a natural dessert comprehensive index. And based on the evaluation model, combining high-sensitivity three-dimensional seismic attributes related to pore permeability and gas content, and fusing and outputting a natural dessert comprehensive index three-dimensional evaluation model. The method has the beneficial effects that the'natural dessert 'of the low-permeability gas reservoir can be intuitively and accurately predicted at low cost, and the natural productivity potential of the reservoir is quantitatively evaluated.
Need to check novelty before this filing date? Find Prior Art